Research on Intelligent Recommendation Algorithm of Short Videos Based on Graph Neural Network
DOI:
https://doi.org/10.62486/latia2025347Keywords:
Graph Neural Network, Multimodal recommendation, Self-Supervised Learning, short video, personalizationAbstract
The rapid development of short video platforms has put forward higher requirements for the accuracy and personalization of content recommendation systems. In this paper, a short video recommendation algorithm based on Graph Neural Network (GNN) is studied, which improves the recommendation performance by fusing multimodal features such as video, audio, and text. The key technologies such as graph convolution neural network, graph attention network and graph pooling operator are analyzed, and a multimodal recommendation framework is constructed by combining self-supervised contrastive learning and local feature encoder to effectively deal with complex user-content interactions. In this paper, several algorithms are compared on TikTok and MovieLens datasets. The experimental results show that the SHL algorithm significantly improves the recommendation accuracy and user personalized satisfaction on TikTok and MovieLens datasets, which is generalizable.
References
Zhao Z. Analysis on the “Douyin (Tiktok) Mania” phenomenon based on recommendation algorithms[C]//E3S Web of Conferences. EDP Sciences, 2021, 235: 03029. DOI: https://doi.org/10.1051/e3sconf/202123503029
Zhang M, Liu Y. A commentary of TikTok recommendation algorithms in MIT Technology Review 2021[J]. Fundamental Research, 2021, 1(6): 846-847. DOI: https://doi.org/10.1016/j.fmre.2021.11.015
Deldjoo Y, Schedl M, Hidasi B, et al. Multimedia recommender systems: Algorithms and challenges[M]//Recommender systems handbook. New York, NY: Springer US, 2021: 973-1014. DOI: https://doi.org/10.1007/978-1-0716-2197-4_25
Yanti D, Subagja A D, Nurhayati S, et al. Short Videos & Social Media Algorithms: Effective Communication in Tourism Marketing[J]. International Journal of Artificial Intelligence Research, 2024, 6(1.2).
Kirdemir B, Kready J, Mead E, et al. Examining video recommendation bias on YouTube[C]//International Workshop on Algorithmic Bias in Search and Recommendation. Cham: Springer International Publishing, 2021: 106-116. DOI: https://doi.org/10.1007/978-3-030-78818-6_10
Zhao H, Wagner C. How TikTok leads users to flow experience: investigating the effects of technology affordances with user experience level and video length as moderators[J]. Internet Research, 2022, 33(2): 820-849. DOI: https://doi.org/10.1108/INTR-08-2021-0595
Khoo O. Picturing diversity: Netflix’s inclusion strategy and the Netflix recommender algorithm (NRA)[J]. Television & New Media, 2023, 24(3): 281-297. DOI: https://doi.org/10.1177/15274764221102864
Fiallos A, Fiallos C, Figueroa S. Tiktok and education: Discovering knowledge through learning videos[C]//2021 Eighth International Conference on EDemocracy & EGovernment (ICEDEG). IEEE, 2021: 172-176. DOI: https://doi.org/10.1109/ICEDEG52154.2021.9530988
Qin Y, Omar B, Musetti A. The addiction behavior of short-form video app TikTok: The information quality and system quality perspective[J]. Frontiers in Psychology, 2022, 13: 932805. DOI: https://doi.org/10.3389/fpsyg.2022.932805
Zhan R, Pei C, Su Q, et al. Deconfounding duration bias in watch-time prediction for video recommendation[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2022: 4472-4481. DOI: https://doi.org/10.1145/3534678.3539092
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Qiuye Guo, Sanghyun Kim (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
